# Exploiting Local Features from Deep Networks for Image Retrieval

arXiv: https://arxiv.org/abs/1504.05133 · HTML: https://mlsanity.com/paper/1504.05133/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2015.

## Built on by (most cited first, 15 of 15)

- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning](https://mlsanity.com/paper/2102.10680/) (2021)
- [Visual Search at Alibaba](https://mlsanity.com/paper/2102.04674/) (2021)
- [Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval](https://mlsanity.com/paper/2308.06748/) (2023)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [Place recognition survey: An update on deep learning approaches](https://mlsanity.com/paper/2106.10458/) (2021)
- [Investigating the Vision Transformer Model for Image Retrieval Tasks](https://mlsanity.com/paper/2101.03771/) (2021)
- [Content-Based Medical Image Retrieval with Opponent Class Adaptive Margin Loss](https://mlsanity.com/paper/2211.15371/) (2022)
- [Deep Features for CBIR with Scarce Data using Hebbian Learning](https://mlsanity.com/paper/2205.08935/) (2022)
- [BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval](https://mlsanity.com/paper/2207.04211/) (2022)
- [Contrastive Supervised Distillation for Continual Representation Learning](https://mlsanity.com/paper/2205.05476/) (2022)
- [Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features](https://mlsanity.com/paper/2210.02401/) (2022)
- [Compressible and Searchable: AI-native Multi-Modal Retrieval System with Learned Image Compression](https://mlsanity.com/paper/2404.10234/) (2024)
- [CBIR using Pre-Trained Neural Networks](https://mlsanity.com/paper/2110.14455/) (2021)
- [Reference Based Color Transfer for Medical Volume Rendering](https://mlsanity.com/paper/2210.08083/) (2022)

## Abstract (arXiv)

Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give the best performance, as they do in classification. We show that for instance-level image retrieval, lower layers often perform better than the last layers in convolutional neural networks. We present an approach for extracting convolutional features from different layers of the networks, and adopt VLAD encoding to encode features into a single vector for each image. We investigate the effect of different layers and scales of input images on the performance of convolutional features using the recent deep networks OxfordNet and GoogLeNet. Experiments demonstrate that intermediate layers or higher layers with finer scales produce better results for image retrieval, compared to the last layer. When using compressed 128-D VLAD descriptors, our method obtains state-of-the-art results and outperforms other VLAD and CNN based approaches on two out of three test datasets. Our work provides guidance for transferring deep networks trained on image classification to image retrieval tasks.